Forest pest multispectral monitoring and early warning system and method based on Internet of Things

Abstract

The invention relates to the technical field of forest disease and insect pest monitoring, and discloses a forest disease and insect pest multispectral monitoring and early warning system and method based on the Internet of Things, and the system comprises a multispectral monitoring module which is arranged in a forest and is used for carrying out the multispectral image collection of forest vegetation, and the multispectral image comprises at least two spectral images of different wavebands; and the data transmission module is connected with the multispectral monitoring module and is used for transmitting the acquired multispectral image data to a data processing center, and the data transmission is realized based on the Internet of Things technology so as to guarantee stable transmission of the data. Multi-spectral image acquisition is performed on forest vegetation through the multi-spectral monitoring module, spectral images of at least two different wavebands are covered, and feature information of the vegetation under different spectrums is comprehensively captured. And data is transmitted to a data processing center in real time by using the Internet of Things technology, so that whether forest vegetation is infected with diseases and pests and the infection degree can be quickly and accurately determined, and accurate monitoring of the forest diseases and pests is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of forest pest monitoring, in particular to a forest pest multispectral monitoring and early warning system and method based on Internet of Things. BACKGROUND

[0002] The monitoring and early warning of forest pests are of great significance to the protection of forest resources and the stability of the ecological system. In traditional forest pest monitoring methods, manual inspection has always played a dominant role. Manual inspection mainly relies on forest rangers or professional monitoring personnel to regularly enter the forest, and to determine the occurrence of pests by observing with the naked eye and collecting and analyzing vegetation samples. However, this method has many drawbacks. On the one hand, the forest area is vast and the terrain is complex and diverse, and the range covered by manual inspection is extremely limited, making it difficult to conduct comprehensive and detailed monitoring of the entire forest area, which can easily lead to the spread of pests without being detected in time. On the other hand, manual inspection consumes a large amount of manpower, material resources and time, and is greatly affected by natural factors such as weather and season, which cannot guarantee the real-time and continuity of the monitoring data.

[0003] With the development of science and technology, optical monitoring technology has been gradually introduced into the field of forest pest monitoring. For example, satellite remote sensing technology is used to obtain the spectral information of forest vegetation, and the health status and degree of pest infection of the vegetation are indirectly determined by analyzing the reflectivity of the vegetation at different spectral bands. However, the spatial resolution of satellite remote sensing monitoring is relatively low, making it difficult to accurately locate and analyze local pest conditions in detail, and it is easily affected by weather conditions such as cloud cover. In addition, there are also some monitoring systems based on ground optical sensors, which can improve the monitoring accuracy to some extent, but they usually only collect spectral data of a single band, and cannot fully capture the characteristic changes of vegetation in multiple spectral dimensions, limiting the accuracy of pest monitoring.

[0004] In recent years, the rise of Internet of Things technology has brought new opportunities for forest pest monitoring. Internet of Things technology can realize the interconnection between devices and between devices and data processing centers, thereby building a distributed monitoring network. At present, some forest monitoring systems based on Internet of Things have been applied, but these systems mostly focus on the monitoring of forest environmental parameters and do not fully combine multispectral monitoring technology for targeted analysis and early warning of pests. Moreover, these systems often lack deep processing and intelligent analysis capabilities for collected data, and may have problems such as unstable signals and high energy consumption during data transmission, which cannot meet the efficient and accurate forest pest monitoring and early warning requirements.

[0005] Therefore, the present application provides a forest pest multispectral monitoring and early warning system and method based on Internet of Things to solve the above problems. SUMMARY

[0006] In view of the deficiencies of the prior art, the present application provides a forest pest multi-spectral monitoring and early warning system and method based on the Internet of Things, which solves the problems raised in the background art.

[0007] To achieve the above object, the present application is implemented by the following technical scheme: a forest pest multi-spectral monitoring and early warning system based on the Internet of Things, comprising:

[0008] A multi-spectral monitoring module is arranged in the forest for multi-spectral image acquisition of the forest vegetation, wherein the multi-spectral image includes at least two different spectral images of different wave bands;

[0009] A data transmission module is connected to the multi-spectral monitoring module for transmitting the acquired multi-spectral image data to a data processing center, and the data transmission is based on the Internet of Things technology to ensure real-time and stable data transmission;

[0010] A data processing center receives the multi-spectral image data and analyzes and processes the data, including analyzing the multi-spectral image, extracting features, and comparing with a pest characteristic database to determine whether the forest vegetation is infected with pests and the degree of infection;

[0011] An early warning module is connected to the data processing center, and when the data processing center determines that the forest vegetation is infected with pests and reaches a preset early warning threshold, the early warning module sends a corresponding early warning signal;

[0012] The multi-spectral monitoring module includes a plurality of spectral sensors of different wave bands, each spectral sensor acquires a spectral image of a corresponding wave band to realize omnidirectional spectral monitoring of the forest vegetation.

[0013] Through the above technical scheme, the multi-spectral monitoring module acquires multi-spectral image data in the forest, and the data transmission module uses the Internet of Things technology to transmit the data to the data processing center in real time and stably. In the center, through analysis processes such as analysis, feature extraction, and comparison with a pest characteristic database, the vegetation pest condition is determined. If the vegetation infection degree reaches the early warning threshold, the early warning module sends a signal in time to assist in early detection and prevention of forest pests and to protect the health of the forest.

[0014] Preferably, it further comprises a sensor node positioning module connected to the multi-spectral monitoring module for accurately positioning the position of the multi-spectral monitoring module in the forest.

[0015] Through the technical scheme, the accurate determination of the position of the multispectral monitoring module in the forest can quickly lock the specific occurrence of the disease and pest, the spatial accuracy of the monitoring work is improved, the subsequent on-site verification and targeted prevention are facilitated, and the effect of the whole disease and pest monitoring and early warning system is enhanced.

[0016] Preferably, the data transmission module adopts a low-power wide-area network communication technology to reduce system energy consumption, prolong the working time of the system in the field, and ensure stable signal transmission coverage in the complex forest environment.

[0017] Through the technical scheme, the system energy consumption is reduced, the field working time is prolonged, and the stable signal transmission coverage in the complex forest environment is ensured.

[0018] Preferably, the data processing center comprises a data preprocessing submodule, a feature extraction submodule, and a comparison and analysis submodule.

[0019] The data preprocessing submodule is configured to perform denoising, calibration, grayscale transformation, and other preprocessing operations on the multispectral image data transmitted.

[0020] The feature extraction submodule is configured to extract key feature information such as spectral features, texture features, and morphological features of vegetation from the preprocessed multispectral image.

[0021] The comparison and analysis submodule is configured to compare and analyze the extracted feature information with the features in the disease and pest feature database to determine the disease and pest state of the forest vegetation.

[0022] Through the technical scheme, the three submodules work together to systemically process the multispectral image data. The data preprocessing submodule first performs denoising, calibration, and grayscale transformation operations on the data to improve data quality. The feature extraction submodule then extracts key feature information from the processed image. Finally, the comparison and analysis submodule compares these features with the disease and pest feature database to accurately determine the disease and pest state of the forest vegetation, providing a scientific basis for forest health assessment.

[0023] Preferably, the feature data in the disease and pest feature database is established through long-term multispectral image collection and expert manual annotation analysis of forest vegetation under different disease and pest types, and the database can be dynamically updated and expanded with the acquisition of new disease and pest feature data to continuously improve the accuracy and comprehensiveness of the system in monitoring diseases and pests.

[0024] Through the technical scheme, the disease and pest feature database is established based on long-term multispectral image collection and expert annotation, and can be dynamically updated to cover new disease and pest features, thereby providing accurate and comprehensive reference for the comparison and analysis submodule and improving the monitoring accuracy of the system.

[0025] Preferably, the remote monitoring terminal is connected to the data processing center, and the staff can check the forest pest monitoring data, receive early warning information, and remotely control and set parameters of the system at any time and any place through the remote monitoring terminal. The remote monitoring terminal includes a mobile phone, a tablet computer, a computer, or other devices.

[0026] Through the above technical solution, the staff can remotely view the monitoring data, receive early warnings, and remotely control and set system parameters through a mobile phone, a tablet, or a computer, thereby improving the convenience and management efficiency of the system.

[0027] Preferably, the power management module adopts a combination of solar power and rechargeable batteries.

[0028] Through the above technical solution, the system is stably powered by a combination of solar power and rechargeable batteries, ensuring its long-term operation in the wild.

[0029] Preferably, a forest pest multispectral monitoring and early warning method based on the Internet of Things includes the following steps:

[0030] The multispectral monitoring module arranged in the forest collects multispectral images of the forest vegetation, and acquires at least two different spectral images of different wavebands;

[0031] The collected multispectral image data is transmitted to the data processing center based on the Internet of Things technology through the data transmission module;

[0032] In the data processing center, the multispectral image data is analyzed and processed, including analyzing the multispectral image, extracting features, and comparing with the pest characteristic database to determine whether the forest vegetation is infected with pests and the infection degree;

[0033] When it is determined that the forest vegetation is infected with pests and reaches a preset early warning threshold, the corresponding early warning signal is sent through the early warning module.

[0034] Through the above technical solution, through the steps of multispectral image collection, data transmission, analysis and processing, and early warning signal sending, real-time monitoring and timely early warning of forest pests are realized, which helps to protect forest resources and the ecological environment.

[0035] Preferably, the analysis and processing of the multispectral image data specifically includes:

[0036] First, the multispectral image data is preprocessed, including denoising, calibration, and gray scale transformation;

[0037] The key feature information of the vegetation, including spectral features, texture features, and morphological features, is extracted from the preprocessed image.

[0038] Finally, the extracted feature information is compared and analyzed with the features in the pest and disease feature database to determine the pest and disease status of forest vegetation.

[0039] Through the above technical solution, the status of forest vegetation pests and diseases can be accurately judged through preprocessing, feature extraction and comparative analysis, thereby improving monitoring accuracy.

[0040] The present invention provides a multispectral monitoring and early warning system and method for forest pests and diseases based on the Internet of Things. It has the following beneficial effects:

[0041] 1. The present invention uses a multispectral monitoring module to collect multispectral images of forest vegetation, covering spectral images of at least two different bands, comprehensively capturing the characteristic information of vegetation under different spectral conditions. Leveraging Internet of Things technology, the data is transmitted in real time to a data processing center. The data processing center analyzes and extracts features from the multispectral images, and then accurately compares them with a database of pest and disease characteristics. This allows for rapid and accurate determination of the presence and extent of pest infestation in forest vegetation, enabling precise monitoring of forest pests and diseases, effectively improving monitoring efficiency and providing a scientific basis for subsequent prevention and control efforts.

[0042] 2. The present invention performs preprocessing operations such as denoising, calibration, and grayscale conversion on the collected multispectral image data through the data preprocessing submodule to remove interference factors in the data and improve data quality. Combined with low-power wide area network communication technology to ensure real-time and stable transmission of data, the system can obtain and process the latest data in a timely manner, make accurate judgments quickly, effectively improve the accuracy and timeliness of monitoring, and ensure that pests and diseases can be discovered and warned in the early stages of their occurrence.

[0043] 3. The present invention introduces Internet of Things technology and automated monitoring equipment. Workers can view forest pest monitoring data, receive early warning information, and remotely control and set parameters of the system anytime and anywhere through remote monitoring terminals, reducing the workload and cost of manual inspections and improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a data processing and early warning flow chart of the present invention;

[0045] Figure 2 This is a diagram showing the connection relationship of the system modules of the present invention. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the specification of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0047] Please refer to the drawings in the specification of the present application Figure 1 - the drawings in the specification of the present application Figure 2 The embodiments of the present application provide a forest pest and disease multispectral monitoring and early warning system based on Internet of Things, comprising:

[0048] The multispectral monitoring module is arranged in the forest and is used for multispectral image acquisition of the forest vegetation. The multispectral image comprises at least two different waveband spectral images.

[0049] Specifically, under the light condition, the vegetation absorbs, reflects and transmits light of different wavelengths. The growth state of the plant, such as the health degree of the leaf and the chlorophyll content, will show unique spectral response on the specific waveband. The healthy vegetation has high reflectivity in the near-infrared waveband, while the damaged vegetation has reduced reflectivity in the waveband. The multispectral monitoring module acquires the spectral images of the corresponding waveband through a plurality of spectral sensors, so as to comprehensively capture the spectral feature change of the vegetation in the multispectral dimension.

[0050] The data transmission module is connected with the multispectral monitoring module and is used for transmitting the acquired multispectral image data to the data processing center. The data transmission is based on the Internet of Things technology to ensure real-time and stable data transmission.

[0051] Specifically, the data transmission process relies on the advanced Internet of Things technology and realizes long-distance and low-power consumption data transmission by means of the Internet of Things communication protocol such as low-power wide-area network. This transmission mode can effectively ensure the stability of data transmission. Even in a complex forest environment, the reliability of data transmission can be ensured and is not disturbed by factors such as terrain and vegetation. At the same time, the data transmission module has real-time transmission capability, so that the data processing center can obtain the latest multispectral image data in real time, thereby timely analyzing and processing to provide strong support for the monitoring and early warning of forest pests and diseases.

[0052] The data processing center receives the multispectral image data and analyzes and processes the data, including analyzing the multispectral image, extracting features and comparing with the pest and disease feature database to determine whether the forest vegetation is infected with pests and diseases and the infection degree. The data processing center comprises a data preprocessing submodule, a feature extraction submodule and a comparison and analysis submodule.

[0053] The feature extraction submodule is configured to extract spectral features, texture features, and morphological features of the vegetation from the preprocessed multispectral images.

[0054] The comparison and analysis submodule is configured to compare and analyze the extracted features with features in a pest and disease feature database to determine the pest and disease state of the forest vegetation.

[0055] Specifically, the processing procedure of the data processing center includes three steps: data preprocessing, feature extraction, and comparison and analysis.

[0056] The data preprocessing submodule is configured to perform basic processing on the original multispectral image data to improve the quality of the data, including removing noise and interference, calibrating the image, and performing grayscale transformation.

[0057] The feature extraction submodule is configured to extract spectral features, texture features, and morphological features of the vegetation from the preprocessed image data.

[0058] The comparison and analysis submodule is configured to compare and analyze the extracted features with features in a pest and disease feature database to determine the pest and disease state of the forest vegetation.

[0059] The data preprocessing submodule is configured to perform preprocessing operations such as noise removal, calibration, and grayscale transformation on the transmitted multispectral image data.

[0060] The feature data in the pest and disease feature database is established through long-term collection of multispectral images of forest vegetation under different pest and disease types and artificial labeling and analysis by experts, and the database can be dynamically updated and expanded with new pest and disease feature data to continuously improve the accuracy and comprehensiveness of the system in monitoring pests and diseases.

[0061] The warning module is connected to the data processing center, and when the data processing center determines that the forest vegetation is infected with pests and diseases and reaches a preset warning threshold, the warning module sends a corresponding warning signal.

[0062] The multispectral monitoring module includes multiple spectral sensors of different wavebands, and each spectral sensor collects spectral images of the corresponding waveband to achieve full-spectrum monitoring of the forest vegetation.

[0063] Specifically, the leaves of healthy vegetation contain a large amount of chlorophyll, which absorbs light in the visible light region and reflects light in the near-infrared region, so the reflectivity in the near-infrared band is relatively high. On the contrary, the chlorophyll content and cell structure of the leaves of vegetation affected by pests and diseases are damaged, the near-infrared reflectivity is reduced, and the visible light reflectivity may be increased due to the decrease of chlorophyll. By simultaneously collecting spectral images of multiple bands through the multispectral monitoring module, the characteristic information of vegetation in different spectral dimensions can be comprehensively obtained, providing key data support for subsequent data analysis and pest and disease identification.

[0064] The sensor node positioning module is further included, which is connected with the multispectral monitoring module and used for accurately positioning the position of the multispectral monitoring module in the forest.

[0065] Specifically, when the occurrence of pests and diseases is monitored, the accurate position information provided by the sensor node positioning module enables the staff to quickly lock the occurrence location of pests and diseases, thereby providing clear orientation guidance for subsequent field investigation and pest and disease control work. The module adopts advanced positioning technologies such as differential global positioning system or real-time kinematic positioning technology to ensure high accuracy and reliability of positioning, meet the strict requirements for positioning of monitoring equipment under complex forest environment and dense vegetation, and ensure efficient operation of the pest and disease monitoring and early warning system.

[0066] The data transmission module adopts low-power wide-area network communication technology to reduce system energy consumption, prolong the working time of the system in the field, and ensure stable signal transmission coverage in the complex forest environment.

[0067] Specifically, the data transmission module adopts low-power wide-area network communication technology, including LoRa (Long Range Radio) or NB-IoT (Narrow Band Internet of Things), to meet the requirements of the system in terms of energy consumption and signal coverage. Low-power wide-area network technology greatly reduces the energy consumption of the device by optimizing signal modulation, reducing data transmission rate and simplifying protocol stack, so that the system can operate for a long time only relying on battery power supply, which is particularly suitable for the environment in the field where it is difficult to frequently charge or replace the battery.

[0068] The remote monitoring terminal is further included, which is connected with the data processing center, and the staff can check the forest pest and disease monitoring data, receive early warning information, and remotely control and set parameters of the system through the remote monitoring terminal at any time and anywhere. The remote monitoring terminal includes devices such as mobile phones, tablet computers or computers.

[0069] Specifically, the remote monitoring terminal serves as the human-computer interaction interface of the system and is connected to the data processing center through the network. It supports various common electronic devices such as mobile phones, tablet computers or computers, etc. The staff can remotely access the monitoring data of the data processing center by means of the professional software or webpage interface on these devices without going to the forest site. This includes multispectral images, vegetation health indicators and pest and disease analysis results, etc. The terminal also has the function of receiving real-time warning notifications. Once the system detects pests and diseases and reaches the preset threshold, the staff will immediately receive a reminder.

[0070] The power management module adopts a combination of solar power and rechargeable batteries.

[0071] A forest pest and disease multispectral monitoring and early warning method based on the Internet of Things includes the following steps:

[0072] The multispectral monitoring module arranged in the forest is used to collect multispectral images of the forest vegetation, and at least two different spectral images are obtained. The analysis and processing steps of the multispectral image data specifically include:

[0073] First, the multispectral image data is preprocessed, including denoising, calibration, grayscale transformation, etc.

[0074] The key feature information of the vegetation, such as spectral features, texture features and morphological features, is extracted from the preprocessed image.

[0075] Finally, the extracted feature information is compared and analyzed with the features in the pest and disease feature database to determine the pest and disease state of the forest vegetation.

[0076] The collected multispectral image data is transmitted to the data processing center based on the Internet of Things technology through the data transmission module.

[0077] In the data processing center, the multispectral image data is analyzed and processed, including analyzing the multispectral image, extracting features and comparing with the pest and disease feature database to determine whether the forest vegetation is infected with pests and diseases and the degree of infection.

[0078] When it is determined that the forest vegetation is infected with pests and diseases and reaches the preset warning threshold, the corresponding warning signal is sent through the warning module.

[0079] Although embodiments of the present application have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A multispectral monitoring and early warning system for forest pests and diseases based on the Internet of Things, characterized by: include: A multispectral monitoring module is provided in the forest and is used to collect multispectral images of forest vegetation, wherein the multispectral images include spectral images of at least two different bands; A data transmission module is connected to the multispectral monitoring module and is used to transmit the collected multispectral image data to a data processing center. The data transmission is implemented based on the Internet of Things technology to ensure real-time and stable transmission of data; A data processing center receives the multispectral image data and performs analysis and processing on the data, including parsing the multispectral image, extracting features, and comparing the data with a pest and disease feature database to determine whether the forest vegetation is infected with pests and diseases and the degree of infection; An early warning module is connected to the data processing center, and when the data processing center determines that the forest vegetation is infected with pests and diseases and reaches a preset early warning threshold, the early warning module sends a corresponding early warning signal; The multi-spectral monitoring module includes a plurality of spectral sensors of different bands, and each spectral sensor collects spectral images of corresponding bands to achieve all-round spectral monitoring of forest vegetation.

2. The multispectral monitoring and early warning system for forest pests and diseases based on the Internet of Things according to claim 1 is characterized in that: It also includes a sensor node positioning module, which is connected to the multi-spectral monitoring module and is used to accurately locate the position of the multi-spectral monitoring module in the forest.

3. The multispectral monitoring and early warning system for forest pests and diseases based on the Internet of Things according to claim 1 is characterized in that: The data transmission module adopts low-power wide area network communication technology to reduce system energy consumption, extend the system's working time in the field, and ensure stable signal transmission coverage in complex forest environments.

4. The multispectral monitoring and early warning system for forest pests and diseases based on the Internet of Things according to claim 1 is characterized in that: The data processing center includes a data preprocessing submodule, a feature extraction submodule and a comparison and analysis submodule; The data preprocessing submodule is used to perform preprocessing operations such as denoising, calibration, and grayscale conversion on the transmitted multispectral image data; The feature extraction submodule is used to extract key feature information such as spectral features, texture features and morphological features of vegetation from the preprocessed multispectral image; The comparison and analysis submodule compares and analyzes the extracted feature information with the features in the pest and disease feature database to determine the pest and disease status of forest vegetation.

5. The multispectral monitoring and early warning system for forest pests and diseases based on the Internet of Things according to claim 4 is characterized in that: The characteristic data in the pest and disease characteristic database is established through long-term multispectral image collection of forest vegetation under different pest and disease types and expert manual annotation analysis. The database can be dynamically updated and expanded as new pest and disease characteristic data is acquired to continuously improve the accuracy and comprehensiveness of the system's pest and disease monitoring.

6. The multispectral monitoring and early warning system for forest pests and diseases based on the Internet of Things according to claim 1 is characterized in that: It also includes a remote monitoring terminal, which is connected to the data processing center. Staff can use the remote monitoring terminal to view forest pest monitoring data, receive early warning information, and remotely control and set parameters of the system anytime and anywhere. The remote monitoring terminal includes devices such as mobile phones, tablets or computers.

7. The multispectral monitoring and early warning system for forest pests and diseases based on the Internet of Things according to claim 1 is characterized in that: It also includes a power management module, which adopts a combination of solar power supply and rechargeable batteries.

8. A multispectral monitoring and early warning method for forest pests and diseases based on the Internet of Things, characterized by: The following steps are involved: Multispectral images of forest vegetation are collected by a multispectral monitoring module installed in the forest to obtain spectral images of at least two different bands; The collected multispectral image data is transmitted to the data processing center via the data transmission module based on the Internet of Things technology; At a data processing center, the multispectral image data is analyzed and processed, including parsing the multispectral image, extracting features, and comparing the images with a pest and disease feature database to determine whether the forest vegetation is infected with pests and diseases and the extent of the infection; When it is determined that forest vegetation is infected with pests and diseases and reaches the preset warning threshold, a corresponding warning signal is issued through the warning module.

9. The method for multispectral monitoring and early warning of forest pests and diseases based on the Internet of Things according to claim 8, characterized in that: The steps of analyzing and processing the multispectral image data specifically include: First, the multispectral image data is preprocessed by denoising, calibration, grayscale conversion and other operations; Extract key feature information such as spectral characteristics, texture characteristics and morphological characteristics of vegetation from the preprocessed images; Finally, the extracted feature information is compared and analyzed with the features in the pest and disease feature database to determine the pest and disease status of forest vegetation.

Images